Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}

global_step220/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ad1d8a4cc2a13a24a570b45fa37028dc18946ec80af95313e5c04b27af712f
+size 24572212542

global_step220/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07792c39d904fe213426aade034908d53dfa6df3297b8547a0ce3f88e7124608
+size 24572212542

global_step220/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584b22e1f2ef59ec8a01b7ef2c0fae531196f84c83e5418d6570db6ae842c219
+size 24572212542

global_step220/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34031ddbd5987990a6c9c7be7f30c9b19f2f13f4015dc7a3dcd82a622b60ff2a
+size 24572212542

global_step220/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6056816c04d598e56f0deeb599947e753d26df0efc99eb82cc7f9113942337b
+size 202337

global_step220/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ccccce8fc084bf2e5931870badeb9fa1d85f351d34e061931bb9829b4f6405
+size 202337

global_step220/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c3bb78a0f6bf2f16012fb7b60bc190dee49d03fc9d606f25138f608bcec7d0
+size 202337

global_step220/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478e39f9d680581cdc8474d4107cb872aa2530240d6257c698461424b0795fc2
+size 202337

latest

@@ -0,0 +1 @@
+global_step220

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f10241cc7d3f86fc856feaf8eefb2963dd762c2b4dd3b7ea1ee0359029a2165
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aca68d899dfd0e72c94980ee720910df3b9e9a45b1232d83b3ab7ddf7a8706d
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700bdaa044afad4693d6e328d49fb1884f2947982c4abfc462c2cef10736643b
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5106e5ea9bf4943cf6de9af96a0b199e8b67e69bd100b1460694241fcf254486
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e0e97bfaded76707bf1e6997b389b9451dc76c3bb67e11f467592173441b86
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022727272727272728,
+      "grad_norm": 26.87245830061202,
+      "learning_rate": 0.0,
+      "loss": 1.0691,
+      "step": 1
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 24.119318241718858,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.989,
+      "step": 2
+    },
+    {
+      "epoch": 0.06818181818181818,
+      "grad_norm": 24.494901097246274,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9827,
+      "step": 3
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 8.720154396981934,
+      "learning_rate": 1e-05,
+      "loss": 0.6482,
+      "step": 4
+    },
+    {
+      "epoch": 0.11363636363636363,
+      "grad_norm": 4.966678220163427,
+      "learning_rate": 9.999476022424688e-06,
+      "loss": 0.5896,
+      "step": 5
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 2.206240528335694,
+      "learning_rate": 9.997904199519748e-06,
+      "loss": 0.392,
+      "step": 6
+    },
+    {
+      "epoch": 0.1590909090909091,
+      "grad_norm": 3.9617287120048257,
+      "learning_rate": 9.995284860725162e-06,
+      "loss": 0.4349,
+      "step": 7
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.7218886368671966,
+      "learning_rate": 9.991618555030848e-06,
+      "loss": 0.3502,
+      "step": 8
+    },
+    {
+      "epoch": 0.20454545454545456,
+      "grad_norm": 1.3224686041620617,
+      "learning_rate": 9.986906050861595e-06,
+      "loss": 0.342,
+      "step": 9
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 1.4655470659379455,
+      "learning_rate": 9.981148335916e-06,
+      "loss": 0.3311,
+      "step": 10
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.099411259913016,
+      "learning_rate": 9.974346616959476e-06,
+      "loss": 0.3786,
+      "step": 11
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 1.5150343483501494,
+      "learning_rate": 9.966502319571303e-06,
+      "loss": 0.2944,
+      "step": 12
+    },
+    {
+      "epoch": 0.29545454545454547,
+      "grad_norm": 1.8955486495667653,
+      "learning_rate": 9.95761708784585e-06,
+      "loss": 0.3586,
+      "step": 13
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 1.0770593717657149,
+      "learning_rate": 9.94769278404799e-06,
+      "loss": 0.3189,
+      "step": 14
+    },
+    {
+      "epoch": 0.3409090909090909,
+      "grad_norm": 1.8091317213751315,
+      "learning_rate": 9.936731488222776e-06,
+      "loss": 0.3416,
+      "step": 15
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 2.29274261320313,
+      "learning_rate": 9.924735497759497e-06,
+      "loss": 0.3399,
+      "step": 16
+    },
+    {
+      "epoch": 0.38636363636363635,
+      "grad_norm": 1.269837989850999,
+      "learning_rate": 9.911707326910145e-06,
+      "loss": 0.3543,
+      "step": 17
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 1.5013795426439296,
+      "learning_rate": 9.897649706262474e-06,
+      "loss": 0.2903,
+      "step": 18
+    },
+    {
+      "epoch": 0.4318181818181818,
+      "grad_norm": 1.4088618552574337,
+      "learning_rate": 9.882565582167673e-06,
+      "loss": 0.2845,
+      "step": 19
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.5165819472750817,
+      "learning_rate": 9.866458116122852e-06,
+      "loss": 0.316,
+      "step": 20
+    },
+    {
+      "epoch": 0.4772727272727273,
+      "grad_norm": 1.6134481868835353,
+      "learning_rate": 9.849330684108409e-06,
+      "loss": 0.2928,
+      "step": 21
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.1143653341061437,
+      "learning_rate": 9.831186875880467e-06,
+      "loss": 0.276,
+      "step": 22
+    },
+    {
+      "epoch": 0.5227272727272727,
+      "grad_norm": 0.9830408617009574,
+      "learning_rate": 9.812030494218484e-06,
+      "loss": 0.313,
+      "step": 23
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.3736364481102779,
+      "learning_rate": 9.79186555412822e-06,
+      "loss": 0.3023,
+      "step": 24
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "grad_norm": 1.338556634218699,
+      "learning_rate": 9.770696282000245e-06,
+      "loss": 0.3273,
+      "step": 25
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 1.34887345898166,
+      "learning_rate": 9.748527114724111e-06,
+      "loss": 0.3059,
+      "step": 26
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "grad_norm": 1.1465526284754688,
+      "learning_rate": 9.725362698758425e-06,
+      "loss": 0.254,
+      "step": 27
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 1.1328089241339367,
+      "learning_rate": 9.701207889156989e-06,
+      "loss": 0.2727,
+      "step": 28
+    },
+    {
+      "epoch": 0.6590909090909091,
+      "grad_norm": 1.4785097164649903,
+      "learning_rate": 9.676067748551232e-06,
+      "loss": 0.314,
+      "step": 29
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 1.2861366584159655,
+      "learning_rate": 9.64994754608912e-06,
+      "loss": 0.3216,
+      "step": 30
+    },
+    {
+      "epoch": 0.7045454545454546,
+      "grad_norm": 1.254630631559985,
+      "learning_rate": 9.622852756330797e-06,
+      "loss": 0.2671,
+      "step": 31
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.4601173539398735,
+      "learning_rate": 9.594789058101154e-06,
+      "loss": 0.283,
+      "step": 32
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.9800010703607837,
+      "learning_rate": 9.565762333299616e-06,
+      "loss": 0.2176,
+      "step": 33
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 1.585779573547555,
+      "learning_rate": 9.535778665667334e-06,
+      "loss": 0.3186,
+      "step": 34
+    },
+    {
+      "epoch": 0.7954545454545454,
+      "grad_norm": 1.3270309012768746,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.334,
+      "step": 35
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 1.2326173009325117,
+      "learning_rate": 9.472965838391187e-06,
+      "loss": 0.2808,
+      "step": 36
+    },
+    {
+      "epoch": 0.8409090909090909,
+      "grad_norm": 1.1558051437795536,
+      "learning_rate": 9.44014984375249e-06,
+      "loss": 0.2117,
+      "step": 37
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 1.0782911468120715,
+      "learning_rate": 9.406403233534134e-06,
+      "loss": 0.2824,
+      "step": 38
+    },
+    {
+      "epoch": 0.8863636363636364,
+      "grad_norm": 1.5406724902243696,
+      "learning_rate": 9.371733080722911e-06,
+      "loss": 0.2335,
+      "step": 39
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.2044242055409695,
+      "learning_rate": 9.33614665187187e-06,
+      "loss": 0.2499,
+      "step": 40
+    },
+    {
+      "epoch": 0.9318181818181818,
+      "grad_norm": 1.2616965501514557,
+      "learning_rate": 9.299651405577286e-06,
+      "loss": 0.2438,
+      "step": 41
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 1.1136761921157818,
+      "learning_rate": 9.262254990915427e-06,
+      "loss": 0.2785,
+      "step": 42
+    },
+    {
+      "epoch": 0.9772727272727273,
+      "grad_norm": 0.9966948364040108,
+      "learning_rate": 9.223965245839367e-06,
+      "loss": 0.2597,
+      "step": 43
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3791645613025802,
+      "learning_rate": 9.184790195536217e-06,
+      "loss": 0.2679,
+      "step": 44
+    },
+    {
+      "epoch": 1.0227272727272727,
+      "grad_norm": 1.179410268749222,
+      "learning_rate": 9.144738050745129e-06,
+      "loss": 0.181,
+      "step": 45
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 1.1815878438627367,
+      "learning_rate": 9.103817206036383e-06,
+      "loss": 0.1863,
+      "step": 46
+    },
+    {
+      "epoch": 1.0681818181818181,
+      "grad_norm": 0.8101413228519797,
+      "learning_rate": 9.062036238051978e-06,
+      "loss": 0.1843,
+      "step": 47
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.9532028129997955,
+      "learning_rate": 9.019403903708036e-06,
+      "loss": 0.1732,
+      "step": 48
+    },
+    {
+      "epoch": 1.1136363636363635,
+      "grad_norm": 0.992565251308887,
+      "learning_rate": 8.975929138359423e-06,
+      "loss": 0.2059,
+      "step": 49
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.9117404975458566,
+      "learning_rate": 8.931621053926998e-06,
+      "loss": 0.2237,
+      "step": 50
+    },
+    {
+      "epoch": 1.1590909090909092,
+      "grad_norm": 0.8003178422788053,
+      "learning_rate": 8.886488936987817e-06,
+      "loss": 0.1334,
+      "step": 51
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 1.2363455579654716,
+      "learning_rate": 8.840542246828763e-06,
+      "loss": 0.2168,
+      "step": 52
+    },
+    {
+      "epoch": 1.2045454545454546,
+      "grad_norm": 1.2347708733857203,
+      "learning_rate": 8.793790613463956e-06,
+      "loss": 0.175,
+      "step": 53
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 1.2303702228676998,
+      "learning_rate": 8.746243835616392e-06,
+      "loss": 0.1787,
+      "step": 54
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2497191463046406,
+      "learning_rate": 8.697911878664222e-06,
+      "loss": 0.1739,
+      "step": 55
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 1.3951861645180035,
+      "learning_rate": 8.648804872552092e-06,
+      "loss": 0.1847,
+      "step": 56
+    },
+    {
+      "epoch": 1.2954545454545454,
+      "grad_norm": 1.245991460551998,
+      "learning_rate": 8.598933109667995e-06,
+      "loss": 0.1351,
+      "step": 57
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 1.32907622391414,
+      "learning_rate": 8.548307042686093e-06,
+      "loss": 0.1546,
+      "step": 58
+    },
+    {
+      "epoch": 1.3409090909090908,
+      "grad_norm": 1.4968562879002865,
+      "learning_rate": 8.496937282375912e-06,
+      "loss": 0.2356,
+      "step": 59
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.9737096273924404,
+      "learning_rate": 8.444834595378434e-06,
+      "loss": 0.1335,
+      "step": 60
+    },
+    {
+      "epoch": 1.3863636363636362,
+      "grad_norm": 1.3589415450025601,
+      "learning_rate": 8.3920099019495e-06,
+      "loss": 0.1363,
+      "step": 61
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 0.8664968714166548,
+      "learning_rate": 8.33847427367102e-06,
+      "loss": 0.1056,
+      "step": 62
+    },
+    {
+      "epoch": 1.4318181818181819,
+      "grad_norm": 1.0430422759251574,
+      "learning_rate": 8.284238931130476e-06,
+      "loss": 0.1827,
+      "step": 63
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 1.0086301864952136,
+      "learning_rate": 8.229315241569177e-06,
+      "loss": 0.1398,
+      "step": 64
+    },
+    {
+      "epoch": 1.4772727272727273,
+      "grad_norm": 0.9279203416268156,
+      "learning_rate": 8.173714716499801e-06,
+      "loss": 0.157,
+      "step": 65
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.1440300758673703,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.1685,
+      "step": 66
+    },
+    {
+      "epoch": 1.5227272727272727,
+      "grad_norm": 1.1751439805537514,
+      "learning_rate": 8.060529912738316e-06,
+      "loss": 0.1572,
+      "step": 67
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 1.0578357890566388,
+      "learning_rate": 8.002969356565822e-06,
+      "loss": 0.1598,
+      "step": 68
+    },
+    {
+      "epoch": 1.5681818181818183,
+      "grad_norm": 1.3193928833299897,
+      "learning_rate": 7.94477940495245e-06,
+      "loss": 0.1854,
+      "step": 69
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 1.2978218132135766,
+      "learning_rate": 7.885972253990104e-06,
+      "loss": 0.1743,
+      "step": 70
+    },
+    {
+      "epoch": 1.6136363636363638,
+      "grad_norm": 1.0105258814245202,
+      "learning_rate": 7.826560229130132e-06,
+      "loss": 0.1987,
+      "step": 71
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 1.004604979048799,
+      "learning_rate": 7.766555782600023e-06,
+      "loss": 0.1795,
+      "step": 72
+    },
+    {
+      "epoch": 1.6590909090909092,
+      "grad_norm": 1.1179470989774414,
+      "learning_rate": 7.70597149079354e-06,
+      "loss": 0.1815,
+      "step": 73
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 1.166448144503895,
+      "learning_rate": 7.644820051634813e-06,
+      "loss": 0.1617,
+      "step": 74
+    },
+    {
+      "epoch": 1.7045454545454546,
+      "grad_norm": 0.9473819093100403,
+      "learning_rate": 7.5831142819169664e-06,
+      "loss": 0.1282,
+      "step": 75
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 1.3707253122758942,
+      "learning_rate": 7.520867114615844e-06,
+      "loss": 0.1843,
+      "step": 76
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.8753193774986169,
+      "learning_rate": 7.458091596179359e-06,
+      "loss": 0.1205,
+      "step": 77
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 0.7554237843642733,
+      "learning_rate": 7.394800883793087e-06,
+      "loss": 0.0983,
+      "step": 78
+    },
+    {
+      "epoch": 1.7954545454545454,
+      "grad_norm": 1.1973348363016902,
+      "learning_rate": 7.331008242622637e-06,
+      "loss": 0.1848,
+      "step": 79
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.1860354581221395,
+      "learning_rate": 7.266727043033386e-06,
+      "loss": 0.1527,
+      "step": 80
+    },
+    {
+      "epoch": 1.8409090909090908,
+      "grad_norm": 1.4128677081083227,
+      "learning_rate": 7.201970757788172e-06,
+      "loss": 0.1602,
+      "step": 81
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 1.296872182127621,
+      "learning_rate": 7.136752959223527e-06,
+      "loss": 0.2184,
+      "step": 82
+    },
+    {
+      "epoch": 1.8863636363636362,
+      "grad_norm": 1.4836645345593107,
+      "learning_rate": 7.071087316405037e-06,
+      "loss": 0.2896,
+      "step": 83
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 1.1976778490053432,
+      "learning_rate": 7.00498759226242e-06,
+      "loss": 0.1659,
+      "step": 84
+    },
+    {
+      "epoch": 1.9318181818181817,
+      "grad_norm": 0.9975231348395474,
+      "learning_rate": 6.938467640704953e-06,
+      "loss": 0.1535,
+      "step": 85
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 0.9648415033602733,
+      "learning_rate": 6.871541403717808e-06,
+      "loss": 0.1753,
+      "step": 86
+    },
+    {
+      "epoch": 1.9772727272727273,
+      "grad_norm": 1.2019101492420445,
+      "learning_rate": 6.8042229084399325e-06,
+      "loss": 0.1562,
+      "step": 87
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9443355724586839,
+      "learning_rate": 6.736526264224101e-06,
+      "loss": 0.1196,
+      "step": 88
+    },
+    {
+      "epoch": 2.022727272727273,
+      "grad_norm": 1.000147993017032,
+      "learning_rate": 6.668465659679714e-06,
+      "loss": 0.1105,
+      "step": 89
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 0.9077637361309605,
+      "learning_rate": 6.600055359698984e-06,
+      "loss": 0.1359,
+      "step": 90
+    },
+    {
+      "epoch": 2.0681818181818183,
+      "grad_norm": 0.8899974700309011,
+      "learning_rate": 6.531309702467159e-06,
+      "loss": 0.1051,
+      "step": 91
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.7405665057218146,
+      "learning_rate": 6.462243096457352e-06,
+      "loss": 0.0949,
+      "step": 92
+    },
+    {
+      "epoch": 2.1136363636363638,
+      "grad_norm": 0.9232739478624769,
+      "learning_rate": 6.392870017410665e-06,
+      "loss": 0.0869,
+      "step": 93
+    },
+    {
+      "epoch": 2.1363636363636362,
+      "grad_norm": 0.907192376363368,
+      "learning_rate": 6.323205005302199e-06,
+      "loss": 0.085,
+      "step": 94
+    },
+    {
+      "epoch": 2.159090909090909,
+      "grad_norm": 0.9510815353153362,
+      "learning_rate": 6.2532626612936035e-06,
+      "loss": 0.1041,
+      "step": 95
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.0694010726357495,
+      "learning_rate": 6.18305764467281e-06,
+      "loss": 0.0933,
+      "step": 96
+    },
+    {
+      "epoch": 2.2045454545454546,
+      "grad_norm": 0.9096286210344772,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.0672,
+      "step": 97
+    },
+    {
+      "epoch": 2.227272727272727,
+      "grad_norm": 1.433917507625707,
+      "learning_rate": 6.041918502931473e-06,
+      "loss": 0.0879,
+      "step": 98
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.9531885718869322,
+      "learning_rate": 5.971013959309038e-06,
+      "loss": 0.0596,
+      "step": 99
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 1.1923953651383123,
+      "learning_rate": 5.8999058998706046e-06,
+      "loss": 0.0788,
+      "step": 100
+    },
+    {
+      "epoch": 2.2954545454545454,
+      "grad_norm": 0.9554826618737247,
+      "learning_rate": 5.828609228227603e-06,
+      "loss": 0.073,
+      "step": 101
+    },
+    {
+      "epoch": 2.3181818181818183,
+      "grad_norm": 1.0620618620218882,
+      "learning_rate": 5.757138887522884e-06,
+      "loss": 0.0852,
+      "step": 102
+    },
+    {
+      "epoch": 2.340909090909091,
+      "grad_norm": 1.1580458870328374,
+      "learning_rate": 5.685509857298781e-06,
+      "loss": 0.1011,
+      "step": 103
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 1.5883148285084483,
+      "learning_rate": 5.613737150357528e-06,
+      "loss": 0.0791,
+      "step": 104
+    },
+    {
+      "epoch": 2.3863636363636362,
+      "grad_norm": 1.2367508056402248,
+      "learning_rate": 5.541835809614704e-06,
+      "loss": 0.0654,
+      "step": 105
+    },
+    {
+      "epoch": 2.409090909090909,
+      "grad_norm": 2.2791052878714653,
+      "learning_rate": 5.469820904946383e-06,
+      "loss": 0.087,
+      "step": 106
+    },
+    {
+      "epoch": 2.4318181818181817,
+      "grad_norm": 1.2009177571989036,
+      "learning_rate": 5.397707530030621e-06,
+      "loss": 0.0754,
+      "step": 107
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 1.24186865246545,
+      "learning_rate": 5.325510799183953e-06,
+      "loss": 0.0676,
+      "step": 108
+    },
+    {
+      "epoch": 2.4772727272727275,
+      "grad_norm": 1.3626254215524685,
+      "learning_rate": 5.253245844193564e-06,
+      "loss": 0.0897,
+      "step": 109
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.2267940513161908,
+      "learning_rate": 5.180927811145818e-06,
+      "loss": 0.081,
+      "step": 110
+    },
+    {
+      "epoch": 2.5227272727272725,
+      "grad_norm": 1.0280554800159314,
+      "learning_rate": 5.108571857251754e-06,
+      "loss": 0.0998,
+      "step": 111
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 1.198523585670272,
+      "learning_rate": 5.036193147670286e-06,
+      "loss": 0.0943,
+      "step": 112
+    },
+    {
+      "epoch": 2.5681818181818183,
+      "grad_norm": 1.0299128746931727,
+      "learning_rate": 4.963806852329715e-06,
+      "loss": 0.0867,
+      "step": 113
+    },
+    {
+      "epoch": 2.590909090909091,
+      "grad_norm": 1.0781930889668705,
+      "learning_rate": 4.891428142748247e-06,
+      "loss": 0.0935,
+      "step": 114
+    },
+    {
+      "epoch": 2.6136363636363638,
+      "grad_norm": 1.3870007299043179,
+      "learning_rate": 4.819072188854183e-06,
+      "loss": 0.1038,
+      "step": 115
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 1.2763920896506822,
+      "learning_rate": 4.746754155806437e-06,
+      "loss": 0.1066,
+      "step": 116
+    },
+    {
+      "epoch": 2.659090909090909,
+      "grad_norm": 1.1553721597437976,
+      "learning_rate": 4.674489200816051e-06,
+      "loss": 0.0727,
+      "step": 117
+    },
+    {
+      "epoch": 2.6818181818181817,
+      "grad_norm": 1.2201292764615486,
+      "learning_rate": 4.602292469969381e-06,
+      "loss": 0.1029,
+      "step": 118
+    },
+    {
+      "epoch": 2.7045454545454546,
+      "grad_norm": 1.0182353763504708,
+      "learning_rate": 4.5301790950536175e-06,
+      "loss": 0.081,
+      "step": 119
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.8638534963225072,
+      "learning_rate": 4.458164190385297e-06,
+      "loss": 0.0743,
+      "step": 120
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.179392830465865,
+      "learning_rate": 4.386262849642474e-06,
+      "loss": 0.1008,
+      "step": 121
+    },
+    {
+      "epoch": 2.7727272727272725,
+      "grad_norm": 0.8679825281753464,
+      "learning_rate": 4.31449014270122e-06,
+      "loss": 0.0493,
+      "step": 122
+    },
+    {
+      "epoch": 2.7954545454545454,
+      "grad_norm": 1.1253980579124658,
+      "learning_rate": 4.2428611124771184e-06,
+      "loss": 0.0848,
+      "step": 123
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 1.0356630565413245,
+      "learning_rate": 4.171390771772399e-06,
+      "loss": 0.068,
+      "step": 124
+    },
+    {
+      "epoch": 2.840909090909091,
+      "grad_norm": 1.3477554175880992,
+      "learning_rate": 4.100094100129396e-06,
+      "loss": 0.1043,
+      "step": 125
+    },
+    {
+      "epoch": 2.8636363636363638,
+      "grad_norm": 0.97866201549117,
+      "learning_rate": 4.028986040690963e-06,
+      "loss": 0.0847,
+      "step": 126
+    },
+    {
+      "epoch": 2.8863636363636362,
+      "grad_norm": 1.1349756610536412,
+      "learning_rate": 3.958081497068528e-06,
+      "loss": 0.0792,
+      "step": 127
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.9146117017482877,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.0611,
+      "step": 128
+    },
+    {
+      "epoch": 2.9318181818181817,
+      "grad_norm": 1.0807764635079844,
+      "learning_rate": 3.816942355327191e-06,
+      "loss": 0.0904,
+      "step": 129
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 1.1271897510030453,
+      "learning_rate": 3.7467373387063973e-06,
+      "loss": 0.0769,
+      "step": 130
+    },
+    {
+      "epoch": 2.9772727272727275,
+      "grad_norm": 1.079134591854598,
+      "learning_rate": 3.6767949946978026e-06,
+      "loss": 0.0936,
+      "step": 131
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0766678958231195,
+      "learning_rate": 3.607129982589337e-06,
+      "loss": 0.0836,
+      "step": 132
+    },
+    {
+      "epoch": 3.022727272727273,
+      "grad_norm": 0.6602194945121888,
+      "learning_rate": 3.5377569035426494e-06,
+      "loss": 0.0432,
+      "step": 133
+    },
+    {
+      "epoch": 3.0454545454545454,
+      "grad_norm": 0.9207788970106073,
+      "learning_rate": 3.468690297532843e-06,
+      "loss": 0.0614,
+      "step": 134
+    },
+    {
+      "epoch": 3.0681818181818183,
+      "grad_norm": 0.7792864367119448,
+      "learning_rate": 3.3999446403010156e-06,
+      "loss": 0.044,
+      "step": 135
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 0.7824193339459661,
+      "learning_rate": 3.331534340320287e-06,
+      "loss": 0.0299,
+      "step": 136
+    },
+    {
+      "epoch": 3.1136363636363638,
+      "grad_norm": 1.035803750265937,
+      "learning_rate": 3.2634737357758994e-06,
+      "loss": 0.0481,
+      "step": 137
+    },
+    {
+      "epoch": 3.1363636363636362,
+      "grad_norm": 0.7826621695998633,
+      "learning_rate": 3.1957770915600696e-06,
+      "loss": 0.0388,
+      "step": 138
+    },
+    {
+      "epoch": 3.159090909090909,
+      "grad_norm": 0.6958054164558033,
+      "learning_rate": 3.1284585962821957e-06,
+      "loss": 0.0351,
+      "step": 139
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.9734916299688532,
+      "learning_rate": 3.0615323592950495e-06,
+      "loss": 0.0458,
+      "step": 140
+    },
+    {
+      "epoch": 3.2045454545454546,
+      "grad_norm": 0.9750452432170936,
+      "learning_rate": 2.995012407737581e-06,
+      "loss": 0.044,
+      "step": 141
+    },
+    {
+      "epoch": 3.227272727272727,
+      "grad_norm": 1.1459789012585446,
+      "learning_rate": 2.9289126835949657e-06,
+      "loss": 0.0663,
+      "step": 142
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 1.1249770693101788,
+      "learning_rate": 2.8632470407764746e-06,
+      "loss": 0.0431,
+      "step": 143
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 0.9864994227169254,
+      "learning_rate": 2.7980292422118282e-06,
+      "loss": 0.0606,
+      "step": 144
+    },
+    {
+      "epoch": 3.2954545454545454,
+      "grad_norm": 1.0092348933533415,
+      "learning_rate": 2.733272956966615e-06,
+      "loss": 0.0538,
+      "step": 145
+    },
+    {
+      "epoch": 3.3181818181818183,
+      "grad_norm": 1.39535927779365,
+      "learning_rate": 2.6689917573773615e-06,
+      "loss": 0.0531,
+      "step": 146
+    },
+    {
+      "epoch": 3.340909090909091,
+      "grad_norm": 0.9511300286527435,
+      "learning_rate": 2.605199116206912e-06,
+      "loss": 0.0382,
+      "step": 147
+    },
+    {
+      "epoch": 3.3636363636363638,
+      "grad_norm": 1.2541730166057663,
+      "learning_rate": 2.5419084038206422e-06,
+      "loss": 0.0419,
+      "step": 148
+    },
+    {
+      "epoch": 3.3863636363636362,
+      "grad_norm": 1.0095638491761618,
+      "learning_rate": 2.4791328853841577e-06,
+      "loss": 0.0434,
+      "step": 149
+    },
+    {
+      "epoch": 3.409090909090909,
+      "grad_norm": 0.8262732933318356,
+      "learning_rate": 2.416885718083035e-06,
+      "loss": 0.0322,
+      "step": 150
+    },
+    {
+      "epoch": 3.4318181818181817,
+      "grad_norm": 0.8137374498919325,
+      "learning_rate": 2.3551799483651894e-06,
+      "loss": 0.0308,
+      "step": 151
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 0.8629006626767369,
+      "learning_rate": 2.294028509206461e-06,
+      "loss": 0.0459,
+      "step": 152
+    },
+    {
+      "epoch": 3.4772727272727275,
+      "grad_norm": 0.75511924638048,
+      "learning_rate": 2.2334442173999794e-06,
+      "loss": 0.0304,
+      "step": 153
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.765294235454733,
+      "learning_rate": 2.17343977086987e-06,
+      "loss": 0.0436,
+      "step": 154
+    },
+    {
+      "epoch": 3.5227272727272725,
+      "grad_norm": 0.8507628894917487,
+      "learning_rate": 2.114027746009897e-06,
+      "loss": 0.0277,
+      "step": 155
+    },
+    {
+      "epoch": 3.5454545454545454,
+      "grad_norm": 1.1371497063801275,
+      "learning_rate": 2.055220595047551e-06,
+      "loss": 0.0463,
+      "step": 156
+    },
+    {
+      "epoch": 3.5681818181818183,
+      "grad_norm": 1.0468638172133997,
+      "learning_rate": 1.9970306434341806e-06,
+      "loss": 0.0354,
+      "step": 157
+    },
+    {
+      "epoch": 3.590909090909091,
+      "grad_norm": 0.8300360380363072,
+      "learning_rate": 1.9394700872616856e-06,
+      "loss": 0.0377,
+      "step": 158
+    },
+    {
+      "epoch": 3.6136363636363638,
+      "grad_norm": 1.2431358466370912,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.0407,
+      "step": 159
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 1.0116784265871086,
+      "learning_rate": 1.826285283500201e-06,
+      "loss": 0.0506,
+      "step": 160
+    },
+    {
+      "epoch": 3.659090909090909,
+      "grad_norm": 0.9351206425735656,
+      "learning_rate": 1.770684758430824e-06,
+      "loss": 0.0383,
+      "step": 161
+    },
+    {
+      "epoch": 3.6818181818181817,
+      "grad_norm": 0.7608293362619839,
+      "learning_rate": 1.7157610688695248e-06,
+      "loss": 0.0251,
+      "step": 162
+    },
+    {
+      "epoch": 3.7045454545454546,
+      "grad_norm": 1.0486186821729864,
+      "learning_rate": 1.6615257263289809e-06,
+      "loss": 0.0354,
+      "step": 163
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.8511206701235292,
+      "learning_rate": 1.607990098050501e-06,
+      "loss": 0.0375,
+      "step": 164
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.9639257216156043,
+      "learning_rate": 1.555165404621567e-06,
+      "loss": 0.0406,
+      "step": 165
+    },
+    {
+      "epoch": 3.7727272727272725,
+      "grad_norm": 0.9665035321570787,
+      "learning_rate": 1.5030627176240903e-06,
+      "loss": 0.0386,
+      "step": 166
+    },
+    {
+      "epoch": 3.7954545454545454,
+      "grad_norm": 0.8935090470273086,
+      "learning_rate": 1.45169295731391e-06,
+      "loss": 0.0351,
+      "step": 167
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 1.1337183807356483,
+      "learning_rate": 1.4010668903320068e-06,
+      "loss": 0.0267,
+      "step": 168
+    },
+    {
+      "epoch": 3.840909090909091,
+      "grad_norm": 1.0191173211814406,
+      "learning_rate": 1.3511951274479096e-06,
+      "loss": 0.03,
+      "step": 169
+    },
+    {
+      "epoch": 3.8636363636363638,
+      "grad_norm": 0.8969739545223467,
+      "learning_rate": 1.3020881213357783e-06,
+      "loss": 0.0433,
+      "step": 170
+    },
+    {
+      "epoch": 3.8863636363636362,
+      "grad_norm": 0.8374168117834856,
+      "learning_rate": 1.2537561643836087e-06,
+      "loss": 0.0272,
+      "step": 171
+    },
+    {
+      "epoch": 3.909090909090909,
+      "grad_norm": 1.0969039495955495,
+      "learning_rate": 1.2062093865360458e-06,
+      "loss": 0.052,
+      "step": 172
+    },
+    {
+      "epoch": 3.9318181818181817,
+      "grad_norm": 0.7906472210562279,
+      "learning_rate": 1.1594577531712392e-06,
+      "loss": 0.0492,
+      "step": 173
+    },
+    {
+      "epoch": 3.9545454545454546,
+      "grad_norm": 0.8214507384737139,
+      "learning_rate": 1.1135110630121837e-06,
+      "loss": 0.036,
+      "step": 174
+    },
+    {
+      "epoch": 3.9772727272727275,
+      "grad_norm": 0.8916597776872088,
+      "learning_rate": 1.0683789460730037e-06,
+      "loss": 0.0358,
+      "step": 175
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9910806202679314,
+      "learning_rate": 1.0240708616405788e-06,
+      "loss": 0.0471,
+      "step": 176
+    },
+    {
+      "epoch": 4.0227272727272725,
+      "grad_norm": 0.8017333339630908,
+      "learning_rate": 9.80596096291967e-07,
+      "loss": 0.0421,
+      "step": 177
+    },
+    {
+      "epoch": 4.045454545454546,
+      "grad_norm": 0.6088709030309449,
+      "learning_rate": 9.379637619480236e-07,
+      "loss": 0.0197,
+      "step": 178
+    },
+    {
+      "epoch": 4.068181818181818,
+      "grad_norm": 0.5056506758915681,
+      "learning_rate": 8.961827939636198e-07,
+      "loss": 0.0161,
+      "step": 179
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.7756562125854171,
+      "learning_rate": 8.552619492548736e-07,
+      "loss": 0.0268,
+      "step": 180
+    },
+    {
+      "epoch": 4.113636363636363,
+      "grad_norm": 0.5669855251712181,
+      "learning_rate": 8.15209804463783e-07,
+      "loss": 0.0202,
+      "step": 181
+    },
+    {
+      "epoch": 4.136363636363637,
+      "grad_norm": 0.6473780755422711,
+      "learning_rate": 7.760347541606339e-07,
+      "loss": 0.0307,
+      "step": 182
+    },
+    {
+      "epoch": 4.159090909090909,
+      "grad_norm": 0.5361573992028992,
+      "learning_rate": 7.377450090845733e-07,
+      "loss": 0.0215,
+      "step": 183
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 0.6191327927742057,
+      "learning_rate": 7.003485944227162e-07,
+      "loss": 0.0297,
+      "step": 184
+    },
+    {
+      "epoch": 4.204545454545454,
+      "grad_norm": 0.7740351242770065,
+      "learning_rate": 6.638533481281323e-07,
+      "loss": 0.0277,
+      "step": 185
+    },
+    {
+      "epoch": 4.2272727272727275,
+      "grad_norm": 0.8036694531204502,
+      "learning_rate": 6.282669192770896e-07,
+      "loss": 0.0337,
+      "step": 186
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.5569549110731221,
+      "learning_rate": 5.935967664658682e-07,
+      "loss": 0.023,
+      "step": 187
+    },
+    {
+      "epoch": 4.2727272727272725,
+      "grad_norm": 0.43268894985216455,
+      "learning_rate": 5.598501562475111e-07,
+      "loss": 0.015,
+      "step": 188
+    },
+    {
+      "epoch": 4.295454545454546,
+      "grad_norm": 0.5798546765255864,
+      "learning_rate": 5.270341616088153e-07,
+      "loss": 0.0161,
+      "step": 189
+    },
+    {
+      "epoch": 4.318181818181818,
+      "grad_norm": 0.667306809133945,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.0207,
+      "step": 190
+    },
+    {
+      "epoch": 4.340909090909091,
+      "grad_norm": 0.5559259388326303,
+      "learning_rate": 4.6422133433266513e-07,
+      "loss": 0.0154,
+      "step": 191
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.48805637239261085,
+      "learning_rate": 4.342376667003845e-07,
+      "loss": 0.0133,
+      "step": 192
+    },
+    {
+      "epoch": 4.386363636363637,
+      "grad_norm": 0.633760717360346,
+      "learning_rate": 4.05210941898847e-07,
+      "loss": 0.0166,
+      "step": 193
+    },
+    {
+      "epoch": 4.409090909090909,
+      "grad_norm": 0.4941494223196582,
+      "learning_rate": 3.771472436692053e-07,
+      "loss": 0.0136,
+      "step": 194
+    },
+    {
+      "epoch": 4.431818181818182,
+      "grad_norm": 0.694276868602463,
+      "learning_rate": 3.500524539108807e-07,
+      "loss": 0.0218,
+      "step": 195
+    },
+    {
+      "epoch": 4.454545454545454,
+      "grad_norm": 0.588819670846474,
+      "learning_rate": 3.239322514487686e-07,
+      "loss": 0.0176,
+      "step": 196
+    },
+    {
+      "epoch": 4.4772727272727275,
+      "grad_norm": 0.5265383444966927,
+      "learning_rate": 2.9879211084301194e-07,
+      "loss": 0.0151,
+      "step": 197
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.44878162692299606,
+      "learning_rate": 2.7463730124157706e-07,
+      "loss": 0.014,
+      "step": 198
+    },
+    {
+      "epoch": 4.5227272727272725,
+      "grad_norm": 0.6569401749445752,
+      "learning_rate": 2.5147288527588964e-07,
+      "loss": 0.0164,
+      "step": 199
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 1.2770158126939868,
+      "learning_rate": 2.2930371799975593e-07,
+      "loss": 0.0218,
+      "step": 200
+    },
+    {
+      "epoch": 4.568181818181818,
+      "grad_norm": 0.5855843139833002,
+      "learning_rate": 2.0813444587178156e-07,
+      "loss": 0.0168,
+      "step": 201
+    },
+    {
+      "epoch": 4.590909090909091,
+      "grad_norm": 0.6376332689792783,
+      "learning_rate": 1.8796950578151785e-07,
+      "loss": 0.0152,
+      "step": 202
+    },
+    {
+      "epoch": 4.613636363636363,
+      "grad_norm": 0.6329781274553996,
+      "learning_rate": 1.6881312411953288e-07,
+      "loss": 0.0111,
+      "step": 203
+    },
+    {
+      "epoch": 4.636363636363637,
+      "grad_norm": 0.9765159855301974,
+      "learning_rate": 1.5066931589159118e-07,
+      "loss": 0.0278,
+      "step": 204
+    },
+    {
+      "epoch": 4.659090909090909,
+      "grad_norm": 0.6973740006107351,
+      "learning_rate": 1.3354188387715017e-07,
+      "loss": 0.022,
+      "step": 205
+    },
+    {
+      "epoch": 4.681818181818182,
+      "grad_norm": 0.5499873946022198,
+      "learning_rate": 1.174344178323289e-07,
+      "loss": 0.0155,
+      "step": 206
+    },
+    {
+      "epoch": 4.704545454545455,
+      "grad_norm": 0.7453329709429668,
+      "learning_rate": 1.0235029373752758e-07,
+      "loss": 0.0274,
+      "step": 207
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.4712400999164701,
+      "learning_rate": 8.829267308985535e-08,
+      "loss": 0.0128,
+      "step": 208
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.791960861976085,
+      "learning_rate": 7.526450224050407e-08,
+      "loss": 0.0206,
+      "step": 209
+    },
+    {
+      "epoch": 4.7727272727272725,
+      "grad_norm": 0.8100989026594698,
+      "learning_rate": 6.326851177722304e-08,
+      "loss": 0.026,
+      "step": 210
+    },
+    {
+      "epoch": 4.795454545454545,
+      "grad_norm": 0.5698845908406204,
+      "learning_rate": 5.230721595201049e-08,
+      "loss": 0.0115,
+      "step": 211
+    },
+    {
+      "epoch": 4.818181818181818,
+      "grad_norm": 0.7463531903553184,
+      "learning_rate": 4.2382912154150244e-08,
+      "loss": 0.0178,
+      "step": 212
+    },
+    {
+      "epoch": 4.840909090909091,
+      "grad_norm": 0.7813627200692648,
+      "learning_rate": 3.3497680428697943e-08,
+      "loss": 0.0163,
+      "step": 213
+    },
+    {
+      "epoch": 4.863636363636363,
+      "grad_norm": 0.66982841564412,
+      "learning_rate": 2.5653383040524228e-08,
+      "loss": 0.0186,
+      "step": 214
+    },
+    {
+      "epoch": 4.886363636363637,
+      "grad_norm": 0.4637052800834321,
+      "learning_rate": 1.8851664083999742e-08,
+      "loss": 0.013,
+      "step": 215
+    },
+    {
+      "epoch": 4.909090909090909,
+      "grad_norm": 0.43304208586446546,
+      "learning_rate": 1.3093949138406892e-08,
+      "loss": 0.0081,
+      "step": 216
+    },
+    {
+      "epoch": 4.931818181818182,
+      "grad_norm": 0.8973836308599885,
+      "learning_rate": 8.381444969151608e-09,
+      "loss": 0.0276,
+      "step": 217
+    },
+    {
+      "epoch": 4.954545454545455,
+      "grad_norm": 0.6757448220546857,
+      "learning_rate": 4.7151392748379095e-09,
+      "loss": 0.0185,
+      "step": 218
+    },
+    {
+      "epoch": 4.9772727272727275,
+      "grad_norm": 0.6378204095313933,
+      "learning_rate": 2.0958004802529297e-09,
+      "loss": 0.0239,
+      "step": 219
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7520281673571331,
+      "learning_rate": 5.239775753129728e-10,
+      "loss": 0.0294,
+      "step": 220
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 75,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 14632660697088.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfb7cfd9b409f81947d5c40d590d787f73e698d70b3a6257639fa43608d9cb0
+size 7608

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)